L-Ewwel Sejħa API Tiegħek
F'din il-paġna
Lezzjoni aġġornata fit-3 ta’ Novembru 2026 ibbażata fuq id-dokumentazzjoni ta’ OpenAI:
temperatureutop_phuma aċċettati biss b’sforz ta’ raġunar ta’none, filwaqt li l-mudelli GPT-5.6 jirraġunaw b’mod awtomatiku (medium). Għalhekk, is-sejħat li jistabbilixxu dawn il-parametri għandhom jispeċifikawreasoning={"effort": "none"}(Responses API) jewreasoning_effort="none"(Chat Completions). Sorsi: Użu ta’ GPT-6 · GPT-5.6 Terra.
L-Ewwel Sejħa API Tiegħek
L-ambjent tiegħek huwa lest: ejja nibdew naħdmu. Inti se tagħmel l-ewwel sejħa tiegħek lejn ir-Responses API, tanalizza l-oġġett li jirritorna, u mbagħad timmanipula l-parametri li jisseparaw tweġiba ġenerika minn waħda utli.
L-Iqsam Sejħa
Żewġ parametri biss huma meħtieġa: model, l-identifikatur tal-mudell li trid tistaqsi, u input, il-prompt tiegħek—jew stringa ta’ test jew lista ta’ messaġġi, kif se naraw ftit.
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.6-terra",
input="What is the difference between Python and JavaScript?"
)
print(response.output_text)
# Result: Python is a versatile language oriented toward data science
# and backend development, while JavaScript is primarily used for
# frontend and backend web development (via Node.js)...
X’Fih Verament ir-Rispons
output_text hija sempliċiment shortcut għall-konvenjenza. L-oġġett response iġorr ukoll l-ID unika tiegħu—essenzjali għall-katina ta’ skambji u biex tfittex sejħat fil-logs tiegħek—il-mudell attwali użat, u breakdown tal-konsum tat-tokens. Agħmilha drawwa li tirreġistra dawn it-tliet biċċiet ta’ informazzjoni mill-ewwel scripts tiegħek. Dan huwa dak li jippermettilek twieġeb il-mistoqsija aktar tard: “Għaliex id-doppju l-kont dan ix-xahar?”
response = client.responses.create(
model="gpt-5.6-terra",
input="Hello, how are you?"
)
# The response text (shortcut)
print(response.output_text)
# The unique ID of the response
print(f"ID: {response.id}")
# The model used
print(f"Model: {response.model}")
# Tokens consumed
print(f"Input tokens: {response.usage.input_tokens}")
print(f"Output tokens: {response.usage.output_tokens}")
print(f"Total tokens: {response.usage.total_tokens}")
# Result:
# Hello! I'm doing very well, thank you. How can I help you?
# ID: resp_abc123xyz
# Model: gpt-5.6-terra
# Input tokens: 14
# Output tokens: 19
# Total tokens: 33
Il-Parametri Li Jimpurtaw
temperature tirregola l-varjabbiltà tal-ġenerazzjoni. F’0.0, il-mudell jagħżel sistematikament il-kontinwazzjoni l-aktar probabbli: dan huwa s-setting għal mistoqsijiet fattwali, estrazzjoni ta’ data, u kull ma trid tirriproduċi bl-istess mod. F’1.0, jesplora aktar, li huwa dak li trid għat-tismija, kitba kreattiva, jew ġenerazzjoni ta’ varjanti.
# Low temperature (0.0) = deterministic, factual
response_factual = client.responses.create(
model="gpt-5.6-terra",
reasoning={"effort": "none"}, # temperature requires effort none
input="What is the capital of Germany?",
temperature=0.0
)
print(response_factual.output_text)
# Result: The capital of Germany is Berlin.
# High temperature (1.0) = creative, varied
response_creative = client.responses.create(
model="gpt-5.6-terra",
reasoning={"effort": "none"}, # temperature requires effort none
input="Invent a name for a literary café.",
temperature=1.0
)
print(response_creative.output_text)
# Result: "The Wandering Pages"—a café where every table bears
# the name of a famous chapter.
Il-parametru instructions jimla r-rwol tal-messaġġ tas-sistema l-qadim: jiddefinixxi r-rwol, it-ton, u l-vincoli li l-mudell għandu jżomm matul l-iskambju kollu, irrispettivament mill-mistoqsija magħmula. Fl-eżempju hawn taħt, l-istess mistoqsija magħmula mingħajr istruzzjonijiet tipproduċi lista ta’ pariri ġenerali; magħhom, tipproduċi riċetti.
response = client.responses.create(
model="gpt-5.6-terra",
instructions="You are an expert in French cuisine. "
"Always respond with recipe suggestions.",
input="I don't know what to do with zucchini."
)
print(response.output_text)
# Result: Here are three ideas for your zucchini:
# 1. Zucchini gratin with goat cheese...
# 2. Provençal ratatouille...
# 3. Cold zucchini velouté with mint...
Fl-aħħar nett, max_output_tokens jillimita t-tul tar-rispons. Din hija salvagwardja baġitarja, mhux istruzzjoni tal-kitba: ir-rispons jinqata’ f’daqqa waħda ladarba jintlaħaq il-limitu. Jekk trid tweġiba qasira u mibnija tajjeb, itlob dan fil-prompt ukoll.
response = client.responses.create(
model="gpt-5.6-terra",
input="Explain general relativity.",
max_output_tokens=100
)
print(response.output_text)
print(f"Tokens used: {response.usage.output_tokens}")
# The response will be truncated at approximately 100 tokens
Nimxu lejn Input Strutturat
Meta stringa sempliċi ma tkunx biżżejjed, input jaċċetta lista ta’ messaġġi. Il-forma minima fiha dawra waħda, iżda l-benefiċċju jidher hekk kif tipprovdi storiku: il-mudell ikollu aċċess għal dak li diġà ntqal u jwieġeb skont dan. Hawnhekk, “progress” jinftiehem fil-kuntest ta’ Python, mhux fl-astratt.
response = client.responses.create(
model="gpt-5.6-terra",
input=[
{
"role": "user",
"content": "Translate to English: Hello world"
}
]
)
print(response.output_text)
# Result: Hello world
# With conversation context
response = client.responses.create(
model="gpt-5.6-terra",
input=[
{
"role": "user",
"content": "My favorite language is Python."
},
{
"role": "assistant",
"content": "Python is an excellent choice! It is very versatile."
},
{
"role": "user",
"content": "Give me a tip to improve."
}
]
)
print(response.output_text)
# Result: To improve in Python, I recommend that you...
Qatt Ma Tħalli Sejħa Mhux Protetta
Is-sejħat tan-netwerk ifallu, u l-keys jiskadu. Tliet eċċezzjonijiet ikopru l-biċċa l-kbira tal-każijiet meta tibda: AuthenticationError għal key nieqsa jew invalida, RateLimitError meta taqbeż it-throughput permess tiegħek, u APIError bħala xibka ta’ sigurtà ġenerika. Lezzjoni sħiħa se terġa’ lura għall-istrateġija sħiħa, iżda mill-lum ‘il quddiem, ilbes is-sejħat tiegħek.
from openai import OpenAI, APIError, AuthenticationError, RateLimitError
client = OpenAI()
try:
response = client.responses.create(
model="gpt-5.6-terra",
input="Hello!"
)
print(response.output_text)
except AuthenticationError:
print("Error: Invalid or missing API key")
except RateLimitError:
print("Error: Too many requests, wait a moment")
except APIError as e:
print(f"API Error: {e.message}")
Biex tikkonsolida dan kollu, ikteb script li jistaqsi tliet mistoqsijiet u jakkumula t-tokens ikkunsmati. Inti se tgħaqqad iċ-ċiklu tas-sejħa, temperatura ta’ 0.0 għal risponsi stabbli, u l-qari ta’ usage—it-tliet riflessi bażiċi.
from openai import OpenAI
client = OpenAI()
questions = [
"What is the largest ocean in the world?",
"Who painted the Mona Lisa?",
"How many planets are in the solar system?"
]
total_tokens = 0
for question in questions:
response = client.responses.create(
model="gpt-5.6-terra",
reasoning={"effort": "none"}, # temperature requires effort none
input=question,
temperature=0.0
)
tokens = response.usage.total_tokens
total_tokens += tokens
print(f"Q: {question}")
print(f"A: {response.output_text}")
print(f" ({tokens} tokens)\n")
print(f"Total: {total_tokens} tokens consumed")
Punti Ewlenin
- Sejħa bażika teħtieġ biss
modeluinput response.output_texttipprovdi t-test tar-risponsresponse.usagejiddettalja l-konsum tat-tokenstemperaturetikkontrolla l-kreattività (0.0 = fattwali, 1.0 = kreattiv)instructionstissostitwixxi l-messaġġ tas-sistema minn Chat Completions- Dejjem immaniġġja l-iżbalji b’blokok try/except